Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    d

    np_max-act · gemini-2.0-flash

    This neuron is essentially inactive—it does not respond to any tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    parsers
    -0.07
     bloodstream
    -0.07
    powered
    -0.06
    122
    -0.06
    Red
    -0.06
     Cross
    -0.06
    FRAME
    -0.06
     Amerikan
    -0.06
    困
    -0.06
     Reuters
    -0.06
    POSITIVE LOGITS
    ('.')[
    0.07
     nn
    0.06
     Countdown
    0.06
     MID
    0.06
     cx
    0.06
    #error
    0.06
    ,mid
    0.06
     Ped
    0.06
     ('
    0.06
    ouver
    0.06
    Act Density 0.001%

    No Known Activations